reedmayhew
/

PocketSurvivor-3B

text-generation-inference

Model card Files Files and versions Community

reedmayhew commited on Jan 17

Commit

eeb5bb6

·

verified ·

1 Parent(s): d7093c3

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -29,7 +29,7 @@ PocketSurvivor-3B is a highly optimized, lightweight language model specifically
 - **Action-Oriented Advice:** Trained on a synthetic dataset designed to provide clear, actionable steps for survival scenarios, ensuring users can quickly apply the information in life-threatening situations.
 - **Mental Well-Being Focus:** Prioritizes emotional support and mental resilience, offering guidance that helps users remain calm and focused under extreme stress.
 - **Broad Scenario Coverage:** Offers solutions for a variety of scenarios, including food and water procurement, shelter building, self-defense, navigation, and first aid.
-- **Offline Usability:** Optimized to run on mobile devices without requiring constant internet connectivity, ensuring accessibility in the most challenging circumstances.
 - **Efficient Training:** Built using [Unsloth](https://github.com/unslothai/unsloth) for rapid training, leveraging Hugging Face’s TRL library to maximize efficiency.
 ## Applications

 - **Action-Oriented Advice:** Trained on a synthetic dataset designed to provide clear, actionable steps for survival scenarios, ensuring users can quickly apply the information in life-threatening situations.
 - **Mental Well-Being Focus:** Prioritizes emotional support and mental resilience, offering guidance that helps users remain calm and focused under extreme stress.
 - **Broad Scenario Coverage:** Offers solutions for a variety of scenarios, including food and water procurement, shelter building, self-defense, navigation, and first aid.
+- **Offline Usability:** Optimized to run on mobile devices without requiring internet connectivity, ensuring accessibility in the most challenging circumstances.
 - **Efficient Training:** Built using [Unsloth](https://github.com/unslothai/unsloth) for rapid training, leveraging Hugging Face’s TRL library to maximize efficiency.
 ## Applications